Lesson 1: my experiments with resnet34 and some questions

[balnazzar (Andrea de Luca)]

@Jeremy, I imagine you are a pretty busy guy, with a lot of stuff to boil down every day. It is truly wonderful that you find time to assist every one of us, with our noob questions, for free, and in detail.
I think I’m speaking for everyone here.

That said, coming to us… The parts of your answers I don’t address, I consider pretty clear.

@jeremy

The ‘discussion’ threads were the in-class discussions during the in-person course. So yup they’re pretty dead! The ‘wiki’ threads are the more active ones now. Having said that, there’s no rules, and it’s really up to you to decide whether you want to start a new thread, on piggy back an existing one. In this case, you’ve got a lot of thoughts and questions, so it seems rather “thread worthy” to me…

Copy that

@jeremy

These images are similar to what you’ll find in imagenet, so it’s well tuned for that. I’m surprised you get 100% however. Is there a chance your validation and test sets overlap?

I admit I didn’t investigate that directly, but I’m inclined to say no, since it’s an official Kaggle dataset. However, they could very well have had them overlapping, just to see how one manages such an issue

@jeremy

Happy to answer. But probably more useful for you for me to help you answer your own question. Do you remember how to view the source of a function? Try using it to dig into lr_find (and the functions it calls) to see if you can find the right source code. Or (maybe even better) try using the python debugger inside the notebook. Once you’ve found the right spot, I think you’ll be able to answer this yourself…

Right. It will be instructive. I used ?? every now and then (I should do it more often), but I never used the integrated debugger.

@jeremy

Based on the shape, I think you have a small dataset.

The train set has just 1098 images, over 10 categories, though… I selected that dataset on purpose: I wanted to discover how such a refined model would perform on a small dataset with just ~100 training examples per category.

@jeremy

The LR finder doesn’t work great on small datasets

Mh, good to know.

@jeremy

PRs would be welcome to implement this. It would be an excellent first fastai contribution project and I’d be happy to help

I hoped to be able to make contributions, no matter how small, once (and if) I would ahve attained more maturity, both in DL and in python development.
But if you (or other senior fastai-ers) say that you would guide me, I’d be more than happy!

@jeremy

The issue is that it doesn’t run enough batches to be very helpful. Try making the batch size 8 or so to make it a bit better

(Once you’ve got more batches going through, the loss will have more of a chance to come down to the levels you’re seeing in your training)

Copy that too.

Let me think a bit about it, I’ll refer to this thread once I encounter problems (that almost surely I’ll have).

Sorry if my counter-reply was 18h delayed. I had a very messed sunday, and if I’m not making mistakes, there are 9 hours between west coast and central europe timezones.
Again, thanks.